CN104778712B - A kind of face chart pasting method and system based on affine transformation - Google Patents
A kind of face chart pasting method and system based on affine transformation Download PDFInfo
- Publication number
- CN104778712B CN104778712B CN201510204631.XA CN201510204631A CN104778712B CN 104778712 B CN104778712 B CN 104778712B CN 201510204631 A CN201510204631 A CN 201510204631A CN 104778712 B CN104778712 B CN 104778712B
- Authority
- CN
- China
- Prior art keywords
- face
- standard
- texture coordinate
- point
- pending
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Processing Or Creating Images (AREA)
- Image Generation (AREA)
Abstract
The invention discloses a kind of face chart pasting method and system based on affine transformation, it is by carrying out standard faces figure standard feature point location and the extraction of standard feature point, and carried out curve fitting using Lagrange's interpolation to the standard feature point of the standard faces figure of extraction, obtain standard texture coordinate, then actual characteristic point location is carried out to pending face figure, and according to the fact characteristic point of the pending face figure, the standard texture coordinate is subjected to Adaptive matching with the corresponding fact characteristic point of the pending face figure using affine transformation, obtain conversion texture coordinate, textures material is finally plotted in the corresponding fact characteristic point position of pending face figure using the conversion texture coordinate, obtain effect face figure；So as to adaptive variously-shaped face position so that the effect face figure after processing is more natural, solves the robustness problem decorated automatically.
Description
Technical field
The present invention relates to technical field of image processing, is particularly a kind of face chart pasting method based on affine transformation and its answers
With the system of this method.
Background technology
In the recent period, the maturation of face recognition technology causes some class APP that dress up to obtain quick development.APP can be utilized
Recognition of face and human face detection tech do special face processing for picture, such as automatic makeup and automatic install additional are adornd.Due to this
Class APP is the built-in material designed using designer mostly, and dressing is added to the corresponding position of face by certain conversion
On, so as to reach the effect of makeup and decoration, therefore, the accurate each position of face that matches naturally becomes the skill of this kind of APP
Art difficult point.
Realize that material is matched with the accurate of face position, in addition to needing accurate face key point identification, it is also necessary to
A kind of adaptive material deformation texture scheme.APP on the market is by recognition of face locating human face's key point mostly at present
Some dressing materials, then will be attached to the target location of target figure by position by some stretching/rotation/translations.This method
The defects of be that image can only do single conversion, and actual face eyebrow shape shape is varied, and such conversion is more difficult
To adapt to various eyebrows, and the simply operation such as stretching/rotation/translation easily tells on distortion.
The content of the invention
The present invention is solved to solve the above problems, provide a kind of face chart pasting method and system based on affine transformation
The robustness problem of automatic decoration, realizes adaptive various face positions of different shapes.
To achieve the above object, the technical solution adopted by the present invention is：
A kind of face chart pasting method based on affine transformation, it is characterised in that comprise the following steps：
10. obtaining standard faces figure, and standard feature point location and the extraction of standard feature point are carried out to standard faces figure；
20. being carried out curve fitting using Lagrange's interpolation to the standard feature point of the standard faces figure of extraction, obtain
Standard texture coordinate；
30. obtaining pending face figure, and actual characteristic point location is carried out to pending face figure；
40. according to the fact characteristic point of the pending face figure, using affine transformation by the standard texture coordinate
Adaptive matching is carried out with the corresponding fact characteristic point of the pending face figure, obtains conversion texture coordinate；
50. textures material is plotted in the corresponding actual special of pending face figure using by the conversion texture coordinate
Sign point position, obtains effect face figure.
Preferably, in the step 10 and step 30, standard feature is carried out to standard faces figure or pending face figure
Point or actual characteristic point location, the standard feature point or fact characteristic point refer to the discrete characteristic point of the key position of face,
Carry out curve fitting in the step 20 to the standard feature point of standard faces figure, being will be each using Lagrange's interpolation
Discrete standard feature point carries out curve fitting according to affiliated face position, obtains the contour shape at the position.
Preferably, in the step 20, standard texture coordinate is obtained by curve matching, is the profile to face position
Characteristic point is supplemented, and obtains standard texture coordinate.
Preferably, the face position refers to facial contour, eyebrow, eyes, nose, lip, and the characteristic point is determined
Position, refers to the height and position, width position, obliquity of facial contour；Eyebrow most inner side, outermost locations, middle part are most
Top position, middle part lowermost position；The inner side canthus positions of eyes, outside canthus position, middle part uppermost position, middle part are most
Lower position, eyeball center；The nose peak position of nose, nose lowest point, wing of nose left-most position, the wing of nose
Right-most position；The left side corners of the mouth position of lip, right side corners of the mouth position, uppermost position in the middle part of upper lip, in the middle part of upper lip most
Uppermost position, lower lip middle part lowermost position in the middle part of lower position, lower lip.
Preferably, in the step 40, using affine transformation by the standard texture coordinate with it is described pending
The corresponding fact characteristic point of face figure carries out Adaptive matching, obtains conversion texture coordinate, further comprises the steps：
41. the standard feature point extracted in preset standard face figure includes at least a, tri- points of b, c and corresponding interpolation point
D, the fact characteristic point of corresponding position includes at least a', tri- points of b', c' in pending face figure；
42. affine transformation matrix M is calculated by triangle △ abc and the △ a'b'c'；
43. the interpolation point d in the standard faces figure to be multiplied by the affine transformation matrix M, pending people is obtained
Correspondence interpolation point d' in face figure, so as to obtain the actual profile shape of the corresponding position of pending face figure；
44. the standard texture coordinate is carried out Adaptive matching according to the actual profile shape, converted
Texture coordinate.
Preferably, in the step 50, textures material is plotted in pending people using the conversion texture coordinate
The corresponding fact characteristic point position of face figure, is the triangle for the corresponding position that pending face figure is drawn by OpenGL, from
And textures material is plotted to the position correspondence position using the conversion texture coordinate, obtain effect face figure.
In addition, present invention also offers a kind of face textures system based on affine transformation, it is characterised in that it includes：
Standard faces feature location module, standard feature point is carried out for obtaining standard faces figure, and to standard faces figure
Positioning and the extraction of standard feature point；
Standard texture Coordinate generation module, its standard feature using Lagrange's interpolation to the standard faces figure of extraction
Point carries out curve fitting, and obtains standard texture coordinate；
Pending extract facial feature module, for obtaining pending face figure, and carries out pending face figure actual
Positioning feature point；
Texture coordinate generation module is converted, it utilizes affine transformation according to the fact characteristic point of the pending face figure
The standard texture coordinate is subjected to Adaptive matching with the corresponding fact characteristic point of the pending face figure, is obtained
Convert texture coordinate；
Effect synthesis module, textures material is plotted in pair of pending face figure using the conversion texture coordinate by it
The fact characteristic point position answered, obtains effect face figure.
Preferably, the conversion texture coordinate generation module further comprises：
Feature point extraction unit, for extraction standard face figure and the standard feature point of the corresponding position of pending face figure
Or fact characteristic point, wherein, the standard feature point extracted in standard faces figure includes at least a, tri- points of b, c and corresponding interpolation
Point d, the fact characteristic point of corresponding position includes at least a', tri- points of b', c' in pending face figure；
Affine transformation matrix computing unit, it calculates affine transformation by triangle △ abc and the △ a'b'c'
Matrix M；
Actual profile shape computing unit, the interpolation point d in the standard faces figure is multiplied by the affine change by it
Matrix M is changed, obtains the correspondence interpolation point d' in pending face figure, so as to obtain the reality of the corresponding position of pending face figure
Contour shape；
Texture coordinate matching unit, it carries out the standard texture coordinate according to the actual profile shape adaptive
It should match, obtain conversion texture coordinate.
The beneficial effects of the invention are as follows：
A kind of the face chart pasting method and system based on affine transformation of the present invention, its by standard faces figure into rower
Quasi- positioning feature point and standard feature point extraction, and the standard feature using Lagrange's interpolation to the standard faces figure of extraction
Point carries out curve fitting, and obtains standard texture coordinate, then carries out actual characteristic point location to pending face figure, and according to institute
The fact characteristic point of pending face figure is stated, using affine transformation by the standard texture coordinate and the pending face
The corresponding fact characteristic point of figure carries out Adaptive matching, obtains conversion texture coordinate, is finally sat using the conversion texture
Textures material is plotted in the corresponding fact characteristic point position of pending face figure by mark, obtains effect face figure；So as to
Adaptive variously-shaped face position so that the effect face figure after processing is more natural, solves the robustness decorated automatically
Problem.
Brief description of the drawings
Attached drawing described herein is used for providing a further understanding of the present invention, forms the part of the present invention, this hair
Bright schematic description and description is used to explain the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is a kind of general flow chart of the face chart pasting method based on affine transformation of the present invention；
Fig. 2 is a kind of structure diagram of the face textures system based on affine transformation of the present invention；
Fig. 3 is the eyebrow outline schematic diagram of the standard faces figure of a specific embodiment of the invention；
Fig. 4 is the eyebrow outline schematic diagram of the pending face figure of a specific embodiment of the invention.
Embodiment
In order to make technical problems, technical solutions and advantages to be solved clearer, clear, tie below
Closing accompanying drawings and embodiments, the present invention will be described in further detail.It should be appreciated that specific embodiment described herein is only used
To explain the present invention, it is not intended to limit the present invention.
As shown in Figure 1, a kind of face chart pasting method based on affine transformation of the present invention, it comprises the following steps：
10. obtaining standard faces figure, and standard feature point location and the extraction of standard feature point are carried out to standard faces figure；
20. being carried out curve fitting using Lagrange's interpolation to the standard feature point of the standard faces figure of extraction, obtain
Standard texture coordinate；
30. obtaining pending face figure, and actual characteristic point location is carried out to pending face figure；
40. according to the fact characteristic point of the pending face figure, using affine transformation by the standard texture coordinate
Adaptive matching is carried out with the corresponding fact characteristic point of the pending face figure, obtains conversion texture coordinate；
50. textures material is plotted in the corresponding actual characteristic of pending face figure using the conversion texture coordinate
Point position, obtains effect face figure.
In the present embodiment, in the step 10 and step 30, standard is carried out to standard faces figure or pending face figure
Characteristic point or actual characteristic point location, the standard feature point or fact characteristic point are primarily referred to as the discrete of the key position of face
Characteristic point, carries out curve fitting the standard feature point of standard faces figure in the step 20, mainly utilizes Lagrange
Interpolation method carries out curve fitting the standard feature point of various discrete according to affiliated face position, obtains the wheel profile at the position
Shape；In the step 20, standard texture coordinate is obtained by curve matching, mainly facial contour feature point is mended
Fill, obtain standard texture coordinate.
Lagrange's interpolation is a kind of polynomial interopolation method, is passed through just on two dimensional surface if it can provide one
The polynomial function of dry known point.(xn, yn) the common n point that assuming that have (x1, y1) (x2, y2) in the plane ..., now makees one
Function f (x) makes its image pass through this n known point, i.e. standard feature point on standard faces figure in the present invention, and it is a more to make n
Item formula pi (x), i=1,2,3..., n so that：
The function f (x) being calculated is：
Finally carried out curve fitting according to the function f (x) to each characteristic point.
The face position is primarily referred to as facial contour, eyebrow, eyes, nose, lip, the positioning feature point,
It is primarily referred to as the height and position, width position, obliquity of facial contour；Eyebrow most inner side, outermost locations, middle part are most
Top position, middle part lowermost position；The inner side canthus positions of eyes, outside canthus position, middle part uppermost position, middle part are most
Lower position, eyeball center；The nose peak position of nose, nose lowest point, wing of nose left-most position, the wing of nose
Right-most position；The left side corners of the mouth position of lip, right side corners of the mouth position, uppermost position in the middle part of upper lip, in the middle part of upper lip most
Uppermost position, lower lip middle part lowermost position in the middle part of lower position, lower lip.
In the step 40, using affine transformation by the standard texture coordinate and the pending face figure
Corresponding fact characteristic point carries out Adaptive matching, obtains conversion texture coordinate, further comprises the steps：
41. the standard feature point extracted in preset standard face figure includes at least a, tri- points of b, c and corresponding interpolation point
D, the fact characteristic point of corresponding position includes at least a', tri- points of b', c' in pending face figure；
42. affine transformation matrix M is calculated by triangle △ abc and the △ a'b'c'；
43. the interpolation point d in the standard faces figure to be multiplied by the affine transformation matrix M, pending people is obtained
Correspondence interpolation point d' in face figure, so as to obtain the actual profile shape of the corresponding position of pending face figure；
44. the standard texture coordinate is carried out Adaptive matching according to the actual profile shape, converted
Texture coordinate.
It is described in detail below by taking eyebrow chart pasting method as an example：
As shown in Figures 3 and 4, point a, b, c, d are the standard feature point that detects on standard faces figure, corresponding, a',
B', c', d' are the corresponding fact characteristic point on pending face figure, and point 1,2,3,4,5,6,7,8 is on standard faces figure
Interpolation point, obtains an affine transformation matrix M, matrix M contains the change of above-mentioned 2 triangles by △ abd and △ a'b'd'
Change information.Correspondingly, we, which will put 1,2,3,4, is multiplied by matrix M, 1,2,3,4 corresponding points 1 ' on pending face figure are obtained,
2’,3’,4’.Similarly, the point on right side 5,6,7,8 is converted to △ bcd and △ the b'c'd' affine transformation matrixs obtained waits to locate
Manage the corresponding points 5 ', 6 ', 7 ', 8 ' on face figure.So, we can utilize the standard feature point marked on standard faces figure
Obtain the corresponding position on pending face figure.It resulting in conversion 4 apex coordinates of texture coordinate and pending
Corresponding 4 apex coordinates of image, each triangle is drawn by OpenGL, so that it is corresponding that textures material is plotted to face
On position.It is advantageous in that shape can preferably be retained using affine transformation, and strong robustness, and standard textures element
The eyebrow texture of material can twist on actual face eyebrow with the conversion of fact characteristic point, and effect is more natural.
In the step 50, textures material is plotted in pair of pending face figure using the conversion texture coordinate
The fact characteristic point position answered, mainly draws the triangle of the corresponding position of pending face figure, so that sharp by OpenGL
Textures material is plotted to the position correspondence position with the conversion texture coordinate, obtains effect face figure.
As shown in Fig. 2, present invention also offers a kind of face textures system based on affine transformation, it includes：
Standard faces feature location modules A, standard feature point is carried out for obtaining standard faces figure, and to standard faces figure
Positioning and the extraction of standard feature point；
Standard texture Coordinate generation module B, its characteristic point using Lagrange's interpolation to the standard faces figure of extraction
Carry out curve fitting, obtain standard texture coordinate；
Pending extract facial feature module C, for obtaining pending face figure, and carries out pending face figure actual
Positioning feature point；
Texture coordinate generation module D is converted, it utilizes affine transformation according to the fact characteristic point of the pending face figure
The standard texture coordinate is subjected to Adaptive matching with the corresponding fact characteristic point of the pending face figure, is obtained
Convert texture coordinate；
Effect synthesis module E, the conversion texture coordinate is plotted in the corresponding actual special of pending face figure by it
Sign point position, obtains effect face figure.
In the present embodiment, the conversion texture coordinate generation module D further comprises：
Feature point extraction cells D 1, the standard feature for extraction standard face figure and the corresponding position of pending face figure
Point or fact characteristic point, wherein, the standard feature point extracted in standard faces figure includes at least a, b, tri- points of c and corresponding slotting
It is worth point d, the fact characteristic point of corresponding position includes at least a', tri- points of b', c' in pending face figure；
Affine transformation matrix computing unit D2, it calculates affine change by triangle △ abc and the △ a'b'c'
Change matrix M；
Actual profile shape calculates cells D 3, and the interpolation point d in the standard faces figure is multiplied by described affine by it
Transformation matrix M, obtains the correspondence interpolation point d' in pending face figure, so as to obtain the reality of the corresponding position of pending face figure
Border contour shape；
Texture coordinate matching unit D4, it carries out the standard texture coordinate certainly according to the actual profile shape
Matching is adapted to, obtains conversion texture coordinate.
It should be noted that each embodiment in this specification is described by the way of progressive, each embodiment weight
Point explanation is all difference with other embodiment, between each embodiment identical similar part mutually referring to.
For system class embodiment, since it is substantially similar to embodiment of the method, so description is fairly simple, related part ginseng
See the part explanation of embodiment of the method.
Herein, term " comprising ", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, from
And process, method, article or the equipment for include a series of elements not only include those key elements, but also including not bright
The other element really listed, or further include as elements inherent to such a process, method, article, or device.Do not having
In the case of more limitations, the key element that is limited by sentence "including a ...", it is not excluded that the process including the key element,
Also there are other identical element in method, article or equipment.In addition, one of ordinary skill in the art will appreciate that on realizing
Stating all or part of step of embodiment can be completed by hardware, can also instruct relevant hardware complete by program
Into the program can be stored in a kind of computer-readable recording medium, and storage medium mentioned above can be read-only
Memory, disk or CD etc..
The preferred embodiment of the present invention has shown and described in described above, it should be understood that the present invention is not limited to this paper institutes
The form of disclosure, is not to be taken as the exclusion to other embodiment, and can be used for various other combinations, modification and environment, and energy
Enough in this paper invented the scope of the idea, it is modified by the technology or knowledge of above-mentioned teaching or association area.And people from this area
The modifications and changes that member is carried out do not depart from the spirit and scope of the present invention, then all should be in the protection of appended claims of the present invention
In the range of.
Claims (8)
1. a kind of face chart pasting method based on affine transformation, it is characterised in that comprise the following steps：
10. obtaining standard faces figure, and standard feature point location and the extraction of standard feature point are carried out to standard faces figure；
20. carrying out curve fitting using Lagrange's interpolation to the standard feature point of the standard faces figure of extraction, standard is obtained
Texture coordinate；
30. obtaining pending face figure, and actual characteristic point location is carried out to pending face figure；
40. according to the fact characteristic point of the pending face figure, using affine transformation by the standard texture coordinate and institute
The corresponding fact characteristic point for the pending face figure stated carries out Adaptive matching, obtains conversion texture coordinate；
50. textures material is plotted in the corresponding fact characteristic point position of pending face figure using the conversion texture coordinate
Put, obtain effect face figure.
A kind of 2. face chart pasting method based on affine transformation according to claim 1, it is characterised in that：The step
10 and step 30 in, the positioning of standard feature point or fact characteristic point, the mark are carried out to standard faces figure or pending face figure
Quasi- characteristic point or fact characteristic point refer to the discrete characteristic point of the key position of face, to standard faces in the step 20
The standard feature point of figure carries out curve fitting, and is to utilize Lagrange's interpolation by the standard feature point of various discrete belonging to
Face position carries out curve fitting, and obtains the contour shape at the position.
A kind of 3. face chart pasting method based on affine transformation according to claim 2, it is characterised in that：The step
In 20, standard texture coordinate is obtained by curve matching, is that facial contour feature point is supplemented, obtains standard texture seat
Mark.
A kind of 4. face chart pasting method based on affine transformation according to Claims 2 or 3, it is characterised in that：Described
Face position refers to facial contour, eyebrow, eyes, nose, lip, the positioning of standard feature point or fact characteristic point,
Refer to the height and position, width position, obliquity of facial contour；Eyebrow most inner side, outermost locations, middle part the top
Position, middle part lowermost position；The inner side canthus position of eyes, outside canthus position, middle part uppermost position, middle part bottom
Position, eyeball center；The nose peak position of nose, nose lowest point, wing of nose left-most position, the wing of nose are most right
Side position；The left side corners of the mouth position of lip, right side corners of the mouth position, upper lip middle part uppermost position, upper lip middle part bottom
Uppermost position, lower lip middle part lowermost position in the middle part of position, lower lip.
A kind of 5. face chart pasting method based on affine transformation according to claim 1, it is characterised in that：The step
It is using affine transformation that the progress of the fact characteristic point of the standard texture coordinate and the pending face figure is adaptive in 40
It should match, obtain conversion texture coordinate, further comprise the steps：
41. the standard feature point extracted in preset standard face figure includes at least a, tri- points of b, c and corresponding interpolation point d, treat
The fact characteristic point of corresponding position includes at least a', tri- points of b', c' in processing face figure；
42. affine transformation matrix M is calculated by triangle △ abc and △ a'b'c'；
43. the interpolation point d in the standard faces figure to be multiplied by the affine transformation matrix M, pending face figure is obtained
In correspondence interpolation point d', so as to obtain the actual profile shape of the corresponding position of pending face figure；
44. the standard texture coordinate is carried out Adaptive matching according to the actual profile shape, conversion texture is obtained
Coordinate.
A kind of 6. face chart pasting method based on affine transformation according to claim 5, it is characterised in that：The step
In 50, textures material is plotted in the fact characteristic point position of pending face figure using the conversion texture coordinate, is logical
The triangle that OpenGL draws the corresponding position of pending face figure is crossed, so that using the conversion texture coordinate that textures are plain
Material is plotted to the position correspondence position, obtains effect face figure.
7. a kind of face textures system based on affine transformation, it is characterised in that it includes：
Standard faces feature location module, standard setting and standard are carried out for obtaining standard faces figure, and to standard faces figure
Feature point extraction；
Standard texture Coordinate generation module, it clicks through the standard feature of the standard faces figure of extraction using Lagrange's interpolation
Row curve matching, obtains standard texture coordinate；
Pending extract facial feature module, actual characteristic is carried out for obtaining pending face figure, and to pending face figure
Point location；
Texture coordinate generation module is converted, it is according to the fact characteristic point of the pending face figure, using affine transformation by institute
The standard texture coordinate stated carries out Adaptive matching with the corresponding fact characteristic point of the pending face figure, is converted
Texture coordinate；
Effect synthesis module, textures material is plotted in the corresponding of pending face figure by it using the conversion texture coordinate
Fact characteristic point position, obtains effect face figure.
A kind of 8. face textures system based on affine transformation according to claim 7, it is characterised in that：The conversion
Texture coordinate generation module further comprises：
Feature point extraction unit, for extraction standard face figure and the standard feature point or reality of the corresponding position of pending face figure
Border characteristic point, wherein, the standard feature point extracted in standard faces figure includes at least a, tri- points of b, c and corresponding interpolation point d,
The fact characteristic point of corresponding position includes at least a', tri- points of b', c' in pending face figure；
Affine transformation matrix computing unit, it calculates affine transformation matrix M by triangle △ abc and △ a'b'c'；
Actual profile shape computing unit, the interpolation point d in the standard faces figure is multiplied by the affine transformation square by it
Battle array M, obtains the correspondence interpolation point d' in pending face figure, so as to obtain the actual profile of the corresponding position of pending face figure
Shape；
Texture coordinate matching unit, the standard texture coordinate is carried out adaptive by it according to the actual profile shape
Match somebody with somebody, obtain conversion texture coordinate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510204631.XA CN104778712B (en) | 2015-04-27 | 2015-04-27 | A kind of face chart pasting method and system based on affine transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510204631.XA CN104778712B (en) | 2015-04-27 | 2015-04-27 | A kind of face chart pasting method and system based on affine transformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104778712A CN104778712A (en) | 2015-07-15 |
| CN104778712B true CN104778712B (en) | 2018-05-01 |
Family
ID=53620158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510204631.XA Active CN104778712B (en) | 2015-04-27 | 2015-04-27 | A kind of face chart pasting method and system based on affine transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104778712B (en) |
Families Citing this family (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447480A (en) * | 2015-12-30 | 2016-03-30 | 吉林纪元时空动漫游戏科技集团股份有限公司 | Face recognition game interactive system |
| CN105915793A (en) * | 2016-05-10 | 2016-08-31 | 北京奇虎科技有限公司 | Intelligent watch shooting processing method and device |
| CN106302124A (en) * | 2016-08-18 | 2017-01-04 | 北京奇虎科技有限公司 | A kind of method adding specially good effect and electronic equipment |
| CN108205795A (en) * | 2016-12-16 | 2018-06-26 | 北京酷我科技有限公司 | Face image processing process and system during a kind of live streaming |
| CN108346171B (en) * | 2017-01-25 | 2021-12-10 | 斑马智行网络(香港)有限公司 | Image processing method, device, equipment and computer storage medium |
| CN106982380A (en) * | 2017-04-20 | 2017-07-25 | 上海极链网络科技有限公司 | The method for implantation of virtual interactive advertisement in internet video |
| CN107481310B (en) * | 2017-08-14 | 2020-05-08 | 迈吉客科技（北京）有限公司 | Image rendering method and system |
| CN107679497B (en) * | 2017-10-11 | 2023-06-27 | 山东新睿信息科技有限公司 | Video face mapping special effect processing method and generating system |
| WO2019071562A1 (en) * | 2017-10-13 | 2019-04-18 | 华为技术有限公司 | Data processing method and terminal |
| CN108205822B (en) * | 2017-12-13 | 2020-09-08 | 中兴通讯股份有限公司 | Picture pasting method and device |
| CN109934058B (en) * | 2017-12-15 | 2021-08-06 | 北京市商汤科技开发有限公司 | Face image processing method, face image processing device, electronic apparatus, storage medium, and program |
| CN108122280A (en) * | 2017-12-20 | 2018-06-05 | 北京搜狐新媒体信息技术有限公司 | The method for reconstructing and device of a kind of three-dimensional point cloud |
| CN108259496B (en) * | 2018-01-19 | 2021-06-04 | 北京市商汤科技开发有限公司 | Method and device for generating special-effect program file package and special effect, and electronic equipment |
| CN108399654B (en) | 2018-02-06 | 2021-10-22 | 北京市商汤科技开发有限公司 | Method and device for generating drawing special effect program file package and drawing special effect |
| CN108388434B (en) * | 2018-02-08 | 2021-03-02 | 北京市商汤科技开发有限公司 | Method and device for generating special-effect program file package and special effect, and electronic equipment |
| CN108492247A (en) * | 2018-03-23 | 2018-09-04 | 成都品果科技有限公司 | A kind of eye make-up chart pasting method based on distortion of the mesh |
| CN113658298A (en) * | 2018-05-02 | 2021-11-16 | 北京市商汤科技开发有限公司 | Method and device for generating special-effect program file package and special effect |
| CN108965692B (en) * | 2018-06-15 | 2021-03-09 | Oppo广东移动通信有限公司 | Sticker setting method and device |
| CN109035373B (en) * | 2018-06-28 | 2022-02-01 | 北京市商汤科技开发有限公司 | Method and device for generating three-dimensional special effect program file package and method and device for generating three-dimensional special effect |
| CN108986016B (en) * | 2018-06-28 | 2021-04-20 | 北京微播视界科技有限公司 | Image beautifying method and device and electronic equipment |
| CN108986227B (en) * | 2018-06-28 | 2022-11-29 | 北京市商汤科技开发有限公司 | Particle special effect program file package generation method and device and particle special effect generation method and device |
| CN108876858A (en) * | 2018-07-06 | 2018-11-23 | 北京字节跳动网络技术有限公司 | Method and apparatus for handling image |
| CN109165571B (en) * | 2018-08-03 | 2020-04-24 | 北京字节跳动网络技术有限公司 | Method and apparatus for inserting image |
| CN110969673B (en) * | 2018-09-30 | 2023-12-15 | 西藏博今文化传媒有限公司 | Live broadcast face-changing interaction realization method, storage medium, equipment and system |
| CN109409274B (en) * | 2018-10-18 | 2020-09-04 | 四川云从天府人工智能科技有限公司 | Face image transformation method based on face three-dimensional reconstruction and face alignment |
| CN109543646A (en) * | 2018-11-30 | 2019-03-29 | 深圳市脸萌科技有限公司 | Face image processing process, device, electronic equipment and computer storage medium |
| CN109584180A (en) * | 2018-11-30 | 2019-04-05 | 深圳市脸萌科技有限公司 | Face image processing process, device, electronic equipment and computer storage medium |
| CN109522869A (en) * | 2018-11-30 | 2019-03-26 | 深圳市脸萌科技有限公司 | Face image processing process, device, terminal device and computer storage medium |
| CN110008911B (en) * | 2019-04-10 | 2021-08-17 | 北京旷视科技有限公司 | Image processing method, image processing device, electronic equipment and computer readable storage medium |
| CN110705346B (en) * | 2019-08-22 | 2022-08-05 | 杭州小影创新科技股份有限公司 | Large-scale human face deformation method |
| CN111047511A (en) * | 2019-12-31 | 2020-04-21 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111178337B (en) * | 2020-01-07 | 2020-12-29 | 南京甄视智能科技有限公司 | Human face key point data enhancement method, device and system and model training method |
| CN111275610B (en) * | 2020-01-08 | 2023-08-18 | 杭州小影创新科技股份有限公司 | Face aging image processing method and system |
| CN112132044B (en) * | 2020-09-24 | 2022-04-22 | 天津锋物科技有限公司 | Face sticker generation method based on face alignment and affine transformation |
| CN114529445A (en) * | 2020-10-30 | 2022-05-24 | 北京字跳网络技术有限公司 | Method and device for drawing special dressing effect, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826217A (en) * | 2010-05-07 | 2010-09-08 | 上海交通大学 | Rapid generation method for facial animation |
| CN104463777A (en) * | 2014-11-11 | 2015-03-25 | 厦门美图之家科技有限公司 | Human-face-based real-time depth of field method |
-
2015
- 2015-04-27 CN CN201510204631.XA patent/CN104778712B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101826217A (en) * | 2010-05-07 | 2010-09-08 | 上海交通大学 | Rapid generation method for facial animation |
| CN104463777A (en) * | 2014-11-11 | 2015-03-25 | 厦门美图之家科技有限公司 | Human-face-based real-time depth of field method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104778712A (en) | 2015-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104778712B (en) | A kind of face chart pasting method and system based on affine transformation | |
| CN102663820B (en) | Three-dimensional head model reconstruction method | |
| CN104408462B (en) | Face feature point method for rapidly positioning | |
| CN107730449B (en) | Method and system for beautifying facial features | |
| CN104123753B (en) | Three-dimensional virtual fitting method based on garment pictures | |
| CN109377557B (en) | Real-time three-dimensional face reconstruction method based on single-frame face image | |
| CN105354876B (en) | A kind of real-time volume fitting method based on mobile terminal | |
| CN106372333A (en) | Method and device for displaying clothes based on face model | |
| CN101339606B (en) | Human face critical organ contour characteristic points positioning and tracking method and device | |
| CN103824253B (en) | Figure five sense organ deformation method based on image local precise deformation | |
| CN107564080B (en) | Face image replacement system | |
| CN102376100A (en) | Single-photo-based human face animating method | |
| CN102402691A (en) | Method for tracking gestures and actions of human face | |
| CN101556699A (en) | Face-based facial aging image synthesis method | |
| CN111028343B (en) | Three-dimensional face model generation method, device, equipment and medium | |
| CN102426712A (en) | Three-dimensional head modeling method based on two images | |
| CN105913416A (en) | Method for automatically segmenting three-dimensional human face model area | |
| CN109801380A (en) | A kind of method, apparatus of virtual fitting, storage medium and computer equipment | |
| CN101751689A (en) | Three-dimensional facial reconstruction method | |
| CN103646416A (en) | Three-dimensional cartoon face texture generation method and device | |
| CN106652037B (en) | Face mapping processing method and device | |
| CN108182397A (en) | A kind of multiple dimensioned face verification method of multi-pose | |
| CN106127743B (en) | The method and system of automatic Reconstruction bidimensional image and threedimensional model accurate relative location | |
| CN106446773A (en) | Automatic robust three-dimensional face detection method | |
| CN109034131A (en) | A kind of semi-automatic face key point mask method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |